def BUILD_ARGPARSE(): parser = argparse.ArgumentParser(description='Processes and Downloads Freesound dataset') parser = add_data_opts(parser) parser.add_argument("--target-dir", default='Freesound_dataset/', type=str, help="Directory to store the dataset.") parser.add_argument("--filter_human_sounds", default='Freesound_dataset/', type=str, help="Directory to store the dataset.") args = parser.parse_args() return args
import os import wget import tarfile import argparse import subprocess from deepspeech_pytorch.data.data_opts import add_data_opts from tqdm import tqdm import shutil from deepspeech_pytorch.data.utils import create_manifest parser = argparse.ArgumentParser( description='Processes and downloads LibriSpeech dataset.') parser = add_data_opts(parser) parser.add_argument("--target-dir", default='LibriSpeech_dataset/', type=str, help="Directory to store the dataset.") parser.add_argument('--files-to-use', default="train-clean-100.tar.gz," "train-clean-360.tar.gz,train-other-500.tar.gz," "dev-clean.tar.gz,dev-other.tar.gz," "test-clean.tar.gz,test-other.tar.gz", type=str, help='list of file names to download') args = parser.parse_args() LIBRI_SPEECH_URLS = { "train": [ "http://www.openslr.org/resources/12/train-clean-100.tar.gz",